We conducted an ecological study linking prevalence of adult asthma symptoms with climate in the 93 New Zealand general electorates. For each electorate, the 12-month period prevalence of self-reported asthma symptoms was determined using a random sample of adults aged 20-44 on the 1991 New Zealand electoral roll. Long-term average climate was estimated using a national climate database and a geographic information system. Asthma prevalence was calculated within quartiles of the exposure variables. Independent effects of climate variables were assessed using linear regression models, with adjustment for confounding by climate, social deprivation, and geographic variables. There was a statistically significant association between asthma prevalence and mean temperature, with the lowest quartile of mean temperature having an approximately 2% lower asthma prevalence. After adjusting for confounding, there was a monotonic increase in asthma prevalence within quartiles of temperature. The results of this study are in agreement with other research suggesting a lower prevalence of asthma at low temperatures. Although on short (day-to-day) time scales, low temperatures may have a direct effect resulting in acute exacerbations of asthma symptoms, warmer average temperatures are associated with increased asthma prevalence. The reasons for this are unclear, although it is possible that on longer term (annual) time scales, higher temperatures are associated with higher levels of allergen exposure.